Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:903447f03d58f6091e77f6c8e86618532694f7851f4bae993e86c4ce18c6f156
+oid sha256:c622298879cc833d1bdcc0a29bd5f4d753b0f9b392bcfe41b3a3720e37227629
 size 496262784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d16ca2f5f37c1c8859b2af1e7c37a0df1c1e053e9beab3ae0485a01ee4349e
+oid sha256:f770627df18e9419658687702329dfc460bbc5339dfe15ca4d75788aa1849e5a
 size 992621963

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c70ce0d856bbf974b0d8a026254698e4f48063d82d2b6e496aefa99327d481
+oid sha256:e52021f1e1b36f10ce9c865a52c47d6a63c888218cae64f20627598071e5030f
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd014c1a4ed62bfbd75417f39dbd6d002ac8b7b9a0b143e7b7bcaa971ce4138
+oid sha256:382f69ae5e5420217ac9e6a070a414359d614c97fe4b4d34a11abdd073f1e7c2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.24,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -798,6 +798,164 @@
       "eval_samples_per_second": 342.906,
       "eval_steps_per_second": 21.553,
       "step": 10000
+    },
+    {
+      "epoch": 0.202,
+      "grad_norm": 0.24885770678520203,
+      "learning_rate": 0.0005429382551153432,
+      "loss": 3.639742431640625,
+      "step": 10100
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 0.22552932798862457,
+      "learning_rate": 0.0005418241804541457,
+      "loss": 3.6341900634765625,
+      "step": 10200
+    },
+    {
+      "epoch": 0.206,
+      "grad_norm": 0.24933825433254242,
+      "learning_rate": 0.0005407005014489372,
+      "loss": 3.6378778076171874,
+      "step": 10300
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.24248844385147095,
+      "learning_rate": 0.0005395672627280085,
+      "loss": 3.630330810546875,
+      "step": 10400
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.20998498797416687,
+      "learning_rate": 0.0005384245092993256,
+      "loss": 3.6162420654296876,
+      "step": 10500
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 0.23281893134117126,
+      "learning_rate": 0.0005372722865487427,
+      "loss": 3.6330096435546877,
+      "step": 10600
+    },
+    {
+      "epoch": 0.214,
+      "grad_norm": 0.2150452584028244,
+      "learning_rate": 0.0005361106402382001,
+      "loss": 3.625997314453125,
+      "step": 10700
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.2066139578819275,
+      "learning_rate": 0.0005349396165039064,
+      "loss": 3.594141540527344,
+      "step": 10800
+    },
+    {
+      "epoch": 0.218,
+      "grad_norm": 0.23046144843101501,
+      "learning_rate": 0.0005337592618545055,
+      "loss": 3.598072204589844,
+      "step": 10900
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2208685725927353,
+      "learning_rate": 0.0005325696231692306,
+      "loss": 3.6059771728515626,
+      "step": 11000
+    },
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.3537567638687666,
+      "eval_loss": 3.57378888130188,
+      "eval_runtime": 6.1179,
+      "eval_samples_per_second": 317.265,
+      "eval_steps_per_second": 19.941,
+      "step": 11000
+    },
+    {
+      "epoch": 0.222,
+      "grad_norm": 0.22270554304122925,
+      "learning_rate": 0.0005313707476960418,
+      "loss": 3.616676940917969,
+      "step": 11100
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.20033609867095947,
+      "learning_rate": 0.0005301626830497491,
+      "loss": 3.6163037109375,
+      "step": 11200
+    },
+    {
+      "epoch": 0.226,
+      "grad_norm": 0.2057274878025055,
+      "learning_rate": 0.0005289454772101221,
+      "loss": 3.593800354003906,
+      "step": 11300
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.20418649911880493,
+      "learning_rate": 0.000527719178519984,
+      "loss": 3.606725769042969,
+      "step": 11400
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.20258976519107819,
+      "learning_rate": 0.000526483835683292,
+      "loss": 3.594194030761719,
+      "step": 11500
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.2198181301355362,
+      "learning_rate": 0.0005252394977632023,
+      "loss": 3.596621398925781,
+      "step": 11600
+    },
+    {
+      "epoch": 0.234,
+      "grad_norm": 0.2138666957616806,
+      "learning_rate": 0.000523986214180122,
+      "loss": 3.5838372802734373,
+      "step": 11700
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 0.22914420068264008,
+      "learning_rate": 0.0005227240347097463,
+      "loss": 3.559365539550781,
+      "step": 11800
+    },
+    {
+      "epoch": 0.238,
+      "grad_norm": 0.23261770606040955,
+      "learning_rate": 0.0005214530094810812,
+      "loss": 3.5759823608398436,
+      "step": 11900
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.21132150292396545,
+      "learning_rate": 0.0005201731889744533,
+      "loss": 3.56010009765625,
+      "step": 12000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.35579436830733646,
+      "eval_loss": 3.5506765842437744,
+      "eval_runtime": 5.6754,
+      "eval_samples_per_second": 342.004,
+      "eval_steps_per_second": 21.496,
+      "step": 12000
     }
   ],
   "logging_steps": 100,
@@ -817,7 +975,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.135504384e+17,
+  "total_flos": 3.7626052608e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null